Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 686 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.4053. Min Act: -0.1700

Data Index: 5803668 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.2651. Min Act: -0.1700

Data Index: 6326976 (Open Web Text)

Max Activating Token Index: 161

Text #2

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.2152. Min Act: -0.1700

Data Index: 3104860 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.1960. Min Act: -0.1700

Data Index: 8551689 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0902. Min Act: -0.1700

Data Index: 461212 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0609. Min Act: -0.1700

Data Index: 520928 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0371. Min Act: -0.1700

Data Index: 6632621 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0360. Min Act: -0.1700

Data Index: 5623489 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0475. Min Act: -0.1700

Data Index: 4050538 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0591. Min Act: -0.1700

Data Index: 254993 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0674. Min Act: -0.1700

Data Index: 4713585 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0603. Min Act: -0.1700

Data Index: 4166365 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0307. Min Act: -0.1700

Data Index: 3733402 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0136. Min Act: -0.1700

Data Index: 8268250 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 5.4053. Min Range: -5.4053

Max Act: 4.9782. Min Act: -0.1700

Data Index: 5621414 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 5.4053. Min Range: -5.4053

Max Act: 4.9675. Min Act: -0.1700

Data Index: 3030563 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 5.4053. Min Range: -5.4053

Max Act: 4.9445. Min Act: -0.1700

Data Index: 7746957 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 5.4053. Min Range: -5.4053

Max Act: 4.9896. Min Act: -0.1700

Data Index: 7383265 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 5.4053. Min Range: -5.4053

Max Act: 5.0064. Min Act: -0.1700

Data Index: 3325324 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 5.4053. Min Range: -5.4053

Max Act: 4.9963. Min Act: -0.1700

Data Index: 7746953 (Open Web Text)

Max Activating Token Index: 123